计算机与现代化 ›› 2024, Vol. 0 ›› Issue (07): 26-35.doi: 10.3969/j.issn.1006-2475.2024.07.005

• 人工智能 • 上一篇    下一篇

基于循环卷积神经网络的排水管网缺陷检测方法

  

  1. (1.广西交科集团有限公司,广西 南宁 530007; 2.深圳大学,广东 深圳 518060)
  • 出版日期:2024-07-25 发布日期:2024-08-07
  • 基金资助:
    国家自然科学基金资助项目(42204148)

Circular Convolutional Neural Network-based Defect Detection Method for#br# Drainage Pipe Networks

  1. (1. Guangxi Transportation Science and Technology Group Co., Ltd., Nanning 530007, China;
    2. Shenzhen University, Shenzhen 518060, China)
  • Online:2024-07-25 Published:2024-08-07

摘要: 市政排水系统关乎城市道路交通安全,故对其状况进行评估非常重要。在发达国家,闭路电视(CCTV)是下水道评估和维护的主要检测工具,却也为其数据处理带来了新的挑战。本文提出一种基于循环卷积神经网络(RCNN)的排水管网缺陷检测方法。RCNN采用残差网络(ResNet)作为特征提取模块,提取排水管网图像序列的视觉特征,采用双向LSTM学习识别时间特征,以完成排水管网缺陷分类的任务。本文方法将图像序列作为一个整体进行识别。训练集、验证集和测试集共包含8800个图像序列, 211200幅图像。经过RCNN模型的训练和测试,测试集的最高准确率为90.3%。将4种不同融合方式引入本文方法并与基于SVM的方法和基于单帧的方法进行了6组对照实验,同时将基于视觉注意力机制的3种融合方法引入本文方并进行了对照实验,实验结果表明,RCNN取平均值的融合实验精度最高(90.3%),召回率达到了0.977,验证了本文方法在工程应用中的可行性。

关键词: 市政排水管网, 卷积神经网络, 循环神经网络

Abstract: Municipal drainage systems are critical to the safety of urban road traffic, so it is important to assess their condition. In developed countries, closed-circuit television (CCTV) is the main detection tool for sewer assessment and maintenance, but it brings new challenges for its data processing. This paper proposes a drainage network defect detection method based on recurrent convolutional neural network (RCNN). The RCNN uses a residual network (ResNet) as feature extraction module to extract visual features of drainage network image sequences, and a bidirectional LSTM is used to learn to identify temporal features to accomplish drainage network defect classification task. The method recognizes image sequences as a whole, and the training set, validation set and test set contain a total of 8800 image sequences, and 211200 images. The data set are trained and tested by the RCNN model, and the highest accuracy rate of the test set is 90.3%. Six sets of control experiments are carried out with four different fusion methods introduced to the proposed method, the SVM-based method and the method based on single frames, as well as three fusion methods based on visual attention mechanism are introduced into the proposed method and control tests are carried out. The experimental results show that the highest accuracy (90.3%) of the fusion experiments is achieved by RCNN taking the average value, and the feasibility analysis of engineering applications is realized, and the recall rate of RCNN reaches 0.977, which confirms the feasibility of the proposed method in engineering applications.

Key words:  , municipal drainage pipe network; convolutional neural network; recurrent neural network

中图分类号: